Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43861
    Prev
    Next
    INDEX
    Explanations

    Tamil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arnold
    -0.09
     σκ
    -0.09
     Burke
    -0.08
    ãn
    -0.08
     Duke
    -0.08
     treinamento
    -0.08
     Postgre
    -0.08
     maneira
    -0.08
     Igor
    -0.08
     التدريب
    -0.08
    POSITIVE LOGITS
    mis
    0.10
     Nadu
    0.09
    Tamil
    0.08
    海外
    0.08
     bleaching
    0.08
     modul
    0.08
    pile
    0.07
     enigmatic
    0.07
     lant
    0.07
    ケ
    0.07
    Activations Density 0.008%

    No Known Activations